Method and system for assessing the synergistic effect of pollution reduction and carbon reduction of a predictive bioretention facility

Abstract

The application discloses a kind of method and system for evaluating the collaborative effect of predicting biological retention facilities to reduce pollution and carbon reduction, belong to the technical field of reducing pollution and carbon reduction, the present application can evaluate the pollution reduction and carbon reduction efficiency of biological retention facilities according to environmental conditions such as different types of antibiotic interference parameters, such as the environment where the biological retention facilities are located;It can also select design parameters and application scenarios according to the desired pollutant removal effect or greenhouse gas emission reduction effect.Meanwhile, the present application is simple to operate, easy to operate, and suitable for wide promotion.It is beneficial to provide support for promoting the widespread application of biological retention facilities in urban stormwater management and greenhouse gas emission reduction.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of pollution reduction and carbon reduction, and more particularly to a method and system for evaluating and predicting the synergistic effect of pollution reduction and carbon reduction of a bioretention facility. BACKGROUND

[0002] At present, human activities have an impact on climate change, and greenhouse gas emissions need to be reduced. Bioretention facilities play an important role in pollution reduction and carbon reduction, and can achieve runoff rainwater pollution purification and carbon sink function in a small area. However, the traditional bioretention facilities focus on the research of runoff pollution control effect, and pay less attention to the greenhouse gas emission reduction effect, which limits the comprehensive benefits of bioretention facilities in urban rainwater management.

[0003] Therefore, in order to improve the pollution reduction and carbon reduction effect of bioretention facilities, the personnel in the field take various ways such as improving the filler and changing the plant species to optimize the design of bioretention facilities, but the differences in pollution removal and greenhouse gas emission reduction effect are large. At the same time, the existing performance evaluation model also focuses on a single pollution control index, and there is still a lack of prediction of the synergistic control effect of multi-factor pollution reduction and carbon reduction, and the parameter optimization of bioretention facilities relies on the experience of trial and error method, and the self-adaptive optimization system under multi-objective constraint has not been developed.

[0004] Therefore, the present application considers predicting the pollution reduction and carbon reduction effect of bioretention facilities according to their own structural parameters and environmental conditions by establishing a model and a database, and selecting the optimal design parameters according to the expected pollution reduction and carbon reduction effect, so as to provide support for promoting the wide application of bioretention facilities in urban rainwater management and greenhouse gas emission reduction. SUMMARY

[0005] In view of the above technical problems, the present application provides a method and system for evaluating and predicting the synergistic effect of pollution reduction and carbon reduction of a bioretention facility, which can evaluate the pollution reduction and carbon reduction effect of the bioretention facility according to the environmental conditions such as different types of antibiotic interference parameters, and can select design parameters and application scenarios according to the expected pollution removal effect or greenhouse gas emission reduction effect. At the same time, the present application is simple to operate, convenient to run, and suitable for wide promotion.

[0006] To achieve the above purpose, the technical scheme adopted by the present application is as follows:

[0007] In a first aspect, the present application provides a method for evaluating and predicting the synergistic effect of pollution reduction and carbon reduction of a bioretention facility, which comprises the following steps:

[0008] S1: collecting the data of pollutant removal rate, greenhouse gas emission and GWP of the bioretention facility with known design parameters and environmental conditions;

[0009] S2: preprocessing the collected data;

[0010] S3: obtaining a pollutant removal rate prediction model and a GWP prediction model of the bioretention facility based on a robust regression analysis method using the preprocessed data; inputting design parameters and environmental factors of a target bioretention facility into the prediction model to obtain a pollutant removal rate prediction value and a GWP prediction value of the target bioretention facility, and evaluating the synergistic performance of pollution reduction and carbon reduction; and establishing a database.

[0011] Further, in S1, the design parameters include respectively planting four kinds of plants, namely, canna, vetiver, iris and eight treasure sedum, and not planting plants; and the environmental conditions include respectively using three different antibiotics, namely, sulfamethoxazole, tetracycline and ciprofloxacin for interference.

[0012] Further, in S2, the collected data is preprocessed using Huber loss function and t test.

[0013] Further, in S3, the calculation formula of the robust regression analysis method is:

[0014] Y =∑β i x i +∈

[0015] In the formula, Y is the dependent variable; x i is the value of the independent variable; β i is the regression coefficient of each independent variable, and ∈ is a constant; the obtaining method of β i and ∈ is:

[0016]

[0017] In the formula, X T is the transpose of the design matrix X; (X T X) -1 is the inverse matrix of the matrix X T X; the obtained matrix is a matrix with n rows, wherein the number in the first row is the constant ∈, and the remaining numbers are the regression coefficients β i of each independent variable.

[0018] Further, in S3, different plant types and added types of antibiotics are used as independent variables to perform stable regression on the pollutant removal rate and the GWP value, wherein the pollutant removal rate is the COD removal rate, and the following is obtained:

[0019] The COD removal rate prediction model is:

[0020] P COD=75.593+0.214×canna lily+2.201×vetiver+0.302×Iris tectorum-0.720×Sedum spectabile-4.684×no plant+6.796×sulfamethoxazole+7.634×tetracycline+3.942×ciprofloxacin;

[0021] In the formula, P COD This is the predicted value for COD removal rate; if the bioretention facility contains plants or antibiotics from the model, the corresponding plant or antibiotic value is recorded as 1, otherwise it is recorded as 0.

[0022] The GWP prediction model is:

[0023] P GWP = 506.499 + 6.771 × Canna indica - 0.647 × Vetiver - 0.949 × Iris tectorum + 0.110 × Sedum spectabile + 8.544 × No plant - 136.491 × Sulfamethoxazole - 120.319 × Tetracycline - 133.533 × Ciprofloxacin;

[0024] In the formula, P GWP This is the predicted value of GWP; if the bioretention facility contains plants or antibiotics from the model, the corresponding plant or antibiotic value is recorded as 1, otherwise it is recorded as 0.

[0025] Furthermore, the method also includes:

[0026] S4: Determine the positive and negative impacts and their proportions of each influencing factor of the target bioretention facility through standardization and normalization, and identify the key influencing factors.

[0027] Furthermore, the method also includes:

[0028] S5: Based on database parameters and key influencing factors, and using the target pollutant removal rate or GWP value, the optimal parameters for the design and construction of the target bioretention facility, as well as its most suitable environmental conditions, are selected using the random forest algorithm.

[0029] Secondly, the present invention also provides a system for evaluating and predicting the synergistic effect of bioretention facilities on pollution reduction and carbon reduction. Using the aforementioned method for evaluating and predicting the synergistic effect of bioretention facilities on pollution reduction and carbon reduction, the system includes:

[0030] The data acquisition module is used to collect data on pollutant removal rate, greenhouse gas emissions, and GWP of bioretention facilities with known design parameters and environmental conditions.

[0031] The data processing module is used to preprocess the collected data;

[0032] The model establishing and application module is used for obtaining the pollutant removal rate prediction model and the GWP prediction model of the bioretention facility based on the robust regression analysis method by using the preprocessed data, inputting the design parameters and environmental factors of the target bioretention facility into the prediction model to obtain the pollutant removal rate prediction value and the GWP prediction value of the target bioretention facility, evaluating the synergistic performance of pollution reduction and carbon reduction, and establishing a database.

[0033] Further, the system further comprises:

[0034] The key influence factor determination module is used for determining the positive and negative influence of each influence factor of the target bioretention facility and the proportion thereof by standardization and normalization processing, and determining the key influence factor.

[0035] Further, the system further comprises:

[0036] The design parameter and environmental condition optimization selection module is used for selecting the optimal parameter of the target bioretention facility design and construction and the most suitable environmental condition thereof by using the random forest algorithm based on the target pollutant removal rate or GWP according to the database parameters and the key influence factor.

[0037] In a third aspect, the present application also provides an electronic device comprising a processor and a memory, wherein the memory stores machine executable instructions capable of being executed by the processor, and the processor executes the machine executable instructions to implement the method for evaluating and predicting the synergistic performance of pollution reduction and carbon reduction of the bioretention facility.

[0038] Compared with the prior art, the present application provides a method for evaluating and predicting the synergistic performance of pollution reduction and carbon reduction of the bioretention facility, which has at least the following beneficial technical effects:

[0039] 1. The present application can predict the pollution reduction and carbon reduction performance of the bioretention facility according to its own construction parameters and environmental conditions, and the prediction effect is better and more comprehensive, which is conducive to providing support for promoting the wide application of the bioretention facility in urban rainwater management and greenhouse gas emission reduction.

[0040] 2. The present application can select the optimal design parameters and application scenarios according to the desired pollutant removal effect or greenhouse gas emission reduction effect.

[0041] 3. The present application is simple to operate and convenient to run, and is suitable for wide promotion.

[0042] Other features and advantages of the present application will be set forth in the following description, and in part will become apparent to those skilled in the art from the description, or can be learned by practice of the present application. The objects and other advantages of the present application can be achieved and obtained by the structure particularly pointed out in the written description and the accompanying drawings.

[0043] The technical solutions of the present application will be further described in detail below with the help of the accompanying drawings and examples. BRIEF DESCRIPTION OF DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the accompanying drawings needed to be used in the embodiments or prior art description will be briefly introduced. Obviously, the accompanying drawings in the following description are some embodiments of the present application, and other accompanying drawings can be obtained by those skilled in the art without creative labor on the premise of the accompanying drawings.

[0045] The accompanying drawings are used to provide a further understanding of the present application, and constitute a part of the specification, which are used together with the embodiments of the present application to explain the present application, and do not constitute a limitation on the present application.

[0046] Figure 1 A flowchart of a method for evaluating and predicting the synergistic effect of reducing pollution and carbon reduction of a biological retention facility is provided for the embodiments of the present application.

[0047] Figure 2 A schematic diagram of an electronic device is provided for the embodiments of the present application. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions in the embodiments of the present application will be clearly and completely described below with the help of the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are some embodiments of the present application, but not all the embodiments.

[0049] In the description of the present application, it should be noted that in some processes described in the specification and the accompanying drawings, a plurality of operations appear in a specific order, but it should be clearly understood that these operations can be executed or in parallel without the order appearing in this text. In addition, various serial numbers and the like are only for the purpose of description, and cannot be understood as indicating or implying relative importance.

[0050] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0051] Reference Figure 1As shown, the embodiment of the present application provides a method for evaluating the synergistic effect of pollution reduction and carbon reduction of a biological retention facility, which can evaluate the pollution reduction and carbon reduction effect of the biological retention facility according to parameters such as fillers, structures and environmental conditions of the biological retention facility, and different types of antibiotic interference, and select design parameters and application scenarios according to the expected pollutant removal effect or greenhouse gas emission reduction effect. Meanwhile, the present application is simple to operate, convenient to run, and suitable for wide promotion. The method mainly includes the following steps:

[0052] In this embodiment, for the biological retention facility with known design parameters and environmental conditions, first, the Huber loss function and t-test are used to preprocess the data such as pollutant removal rate, greenhouse gas emission and global warming potential (Global Warming Potential, hereinafter referred to as GWP) of the biological retention facility;

[0053] Further, based on the robust regression analysis method, a prediction model formula of the pollutant removal rate, greenhouse gas emission and GWP value of the biological retention facility is obtained, and a database is established;

[0054] Further, by inputting the design parameters (such as plant species) and environmental factors (such as antibiotic types and concentrations) of the biological retention facility, the pollutant removal rate, greenhouse gas emission and GWP value under specific conditions can be obtained;

[0055] Further, by standardization and normalization processing, the positive and negative influence of each influencing factor and its proportion are determined, and the main influencing factors (i.e. key influencing factors) are determined. Subsequently, the main influencing factor parameters can be adjusted to improve the pollution reduction and carbon reduction effect of the biological retention facility;

[0056] Further, according to the database parameters, in the case of a target pollutant removal rate or greenhouse gas emission, the optimal parameters for designing and constructing the biological retention facility and the most suitable environmental conditions can be selected based on the random forest algorithm.

[0057] The working principle and specific implementation of the present application will be described in detail as follows:

[0058] In the experiment, five biological retention columns (biological retention facilities) respectively planted with four types of plants, namely canna, vetiver, iris and eight treasure sedum, and no plants were set up, and three groups of parallel experiments were set up for each group to deal with the interference of three different antibiotics, namely sulfamethoxazole, tetracycline and ciprofloxacin. Simulated rainfall was carried out using laboratory prepared simulated rainwater, COD concentration of effluent was detected using rapid digestion spectrophotometry, and removal rate was calculated, and CO2, CH4 and N2O emission were detected using gas chromatography, and GWP value was calculated.

[0059] Based on the experimental data, the COD removal rate and GWP value were taken as dependent variables, and the types of antibiotics and plants were taken as independent variables. First, Huber loss function was used to reduce the influence of outliers, and t-test (p value < 0.05) was used to screen significant variables and eliminate less relevant parameters. Robust regression analysis method was used to establish the prediction model (1):

[0060] Y = ∑β i x i + ∈ (1)

[0061] In the formula, Y is the dependent variable; x i is the value of the independent variable; β i is the regression coefficient of each independent variable, and ∈ is a constant, β i and ∈ are obtained by least squares method, and the specific method is as follows:

[0062] First, add a list of all 1s in the first column of the independent variable matrix to represent the intercept term, and get the design matrix X; the regression coefficient β i is obtained by formula (2):

[0063]

[0064] In the formula, X T is the transpose of the design matrix X; (X T X) -1 is the inverse matrix of the matrix X T X; Y is the observation value vector of the dependent variable. The obtained matrix is a matrix of n rows, where the first row is the constant ∈ in the prediction model (1), and the remaining (n-1) numbers are the regression coefficients β i of each independent variable.

[0065] Further, cross-validation was used to evaluate the stability of the model, and residual analysis was used to optimize the model.

[0066] Under the interference of sulfamethoxazole, tetracycline and ciprofloxacin, respectively, planting canna, vetiver, iris and eight treasure sedum in the bio-retention facilities, and not planting plants in the bio-retention facilities, through repeated experiments, the COD removal rate and GWP value of the bio-retention facilities planted with different plants under the interference of different antibiotics were obtained, and the types of added antibiotics and different plants were taken as independent variables. The COD removal rate and GWP value were respectively subjected to stable regression, and the following results were obtained:

[0067] (1) The prediction model of COD removal rate is:

[0068] P COD= 75.593 + 0.214 x Canna + 2.201 x Vetiver + 0.302 x Iris + 0.720 x Sedum + 4.684 x No plant + 6.796 x Sulfamethoxazole + 7.634 x Tetracycline + 3.942 x Ciprofloxacin;

[0069] In the formula, P COD is the predicted value of COD removal rate (%), and is recorded as 1 if the plant is planted or the antibiotic is added, and is recorded as 0 if not. In the prediction model of COD removal rate, the numerical values of 75.593, 0.214, 2.201, 0.302, 0.720, 4.684, 6.796, 7.634 and 3.942 are obtained from the above formula (2).

[0070] For example, it can be predicted by the model that the COD removal rate of the bioretention facility planted with Vetiver under the interference of Sulfamethoxazole is P COD = 75.593 + 2.201 + 6.796 = 84.59%.

[0071] (2) The prediction model of GWP value emission is:

[0072] In the formula, P GWP = 506.499 + 6.771 x Canna - 0.647 x Vetiver - 0.949 x Iris + 0.110 x Sedum + 8.544 x No plant - 136.491 x Sulfamethoxazole - 120.319 x Tetracycline - 133.533 x Ciprofloxacin;

[0073] In the formula, P GWP is the predicted value of GWP (mg / (m 2 ·h)), and is recorded as 1 if the plant is planted or the antibiotic is added, and is recorded as 0 if not. In the prediction model, the numerical values of 506.499, 6.771, 0.647, 0.949, 0.110, 8.544, 136.491, 120.319 and 133.533 are obtained from the above formula (2).

[0074] For example, it can be predicted by the model that the GWP of the bioretention facility planted with Canna under the interference of Sulfamethoxazole is P GWP = 506.499 + 6.771 - 136.491 = 376.779 mg / (m 2 ·h).

[0075] In a preferred embodiment, the regression coefficients β i of the independent variables in the prediction formula are also standardized and normalized. First, the data is standardized by using formula (3) to eliminate the dimensional influence;

[0076]

[0077] In the formula, u i σ is the mean. i The standard deviation is denoted as .

[0078] Using formula (4) to convert the regression coefficient β in formula (1) i Standardized to be the Beta coefficient β j This is used to represent the effect of changes in the independent variable on the dependent variable:

[0079]

[0080] In the formula, β i For standardized regression coefficients, σ x and σ y These are the standard deviations of the independent and dependent variables, respectively.

[0081] To better compare the differences between different factors, the standardized Beta coefficient is normalized using formula (5), scaling the data to the [-1,1] interval:

[0082]

[0083] In the formula, β represents the coefficients normalized to the interval [-1, 1]. j Let be the standardized Beta coefficients, and max(|β|) be the maximum absolute value of all standardized coefficients. A positive value indicates that this influencing factor has a positive effect on pollutant removal rate and greenhouse gas emissions. A negative value indicates that this influencing factor will reduce pollutant removal rate and greenhouse gas emissions. The larger the absolute value, the greater the impact of this influencing factor on pollutant removal rate and greenhouse gas emissions. Therefore, the main influencing factors can be determined by analyzing the normalized coefficients, and the design parameters can be adjusted according to the environmental conditions to improve the pollution reduction and carbon reduction efficiency of bioretention facilities.

[0084] For example, when predicting the COD removal rate of bioretention facilities with canna lilies, vetiver, iris, and sedum under interference from sulfamethoxazole, tetracycline, and ciprofloxacin, as well as in the case of no plant growth, the following analysis was performed with vetiver planted. The COD removal rate was 0.156 for the planted *Sedum spectabile* and -0.051 for the planted planted *Sedum spectabile*. This indicates that planting *Vegetariana* in the bioretention facility can increase the COD removal rate, while planting *Sedum spectabile* will decrease the COD removal rate. Additionally, planting *Iris tectorum*... Only 0.021, indicating that planting vanilla grass has better effect on improving the COD removal rate of the bioretention facility than planting iris. Therefore, it is predicted that better COD removal effect can be obtained by planting vanilla grass in the bioretention facility.

[0085] According to the random forest algorithm, the existing bioretention facility pollutant removal rate and greenhouse gas emission data under different design parameters (such as biocarbon doping type and proportion, plant type, etc.) and environmental conditions (such as rainfall intensity, temperature, antibiotic interference type and concentration, etc.) are collected from Web of Science, ScienceDirect and other platforms and experiments. The reshape2 package is used to convert the data into a format suitable for modeling. Formula (3) (4) (5) is used to perform regression analysis and standardization processing on the data to screen the main influencing factors. A number of subsets are randomly selected from the data set, a decision tree is constructed using the gbm package, and then a random forest model is constructed using the randomForest package. The dismo package is used to optimize the model parameters and evaluate the model stability through cross-validation. The rpart.plot package is used to visualize the decision tree structure. Through the decision tree structure diagram formed by the database, the pollutant removal rate and greenhouse gas emission can be predicted according to the planned design parameters and environmental conditions. The ggplot2 package is used to visualize the comparison between the predicted results and the actual values. According to the prediction results, it is determined whether the design parameters and environmental conditions meet the target pollutant removal rate and greenhouse gas emission requirements. If not, adjust the design parameters and re-predict.

[0086] From the description of the above embodiments, those skilled in the art can know that the embodiments provided by the present application exemplify the prediction method and influencing factor weight of the COD removal rate and GWP value of the bioretention facility planted with different types of plants under different types of antibiotic interference. Based on this method, the biocarbon addition type and amount, submergence depth, medium layer thickness and other structural parameters of the bioretention facility, as well as the initial concentration of pollutants, rainfall intensity, environmental temperature, dry period and other environmental factors can be introduced. A more comprehensive prediction model of the pollutant removal rate, greenhouse gas emission and synergistic effect of pollution reduction and carbon reduction of the bioretention facility can be established. Based on this model, the pollutant removal effect and greenhouse gas emission of the bioretention facility can be predicted according to its structural parameters and environmental conditions before construction. If it does not meet the expected requirements, it can be adjusted in time. This is conducive to providing support for promoting the widespread application of bioretention facilities in urban rainwater management and greenhouse gas emission reduction.

[0087] Furthermore, embodiments of the present invention also provide a system for evaluating and predicting the synergistic effect of bioretention facilities on pollution reduction and carbon reduction, applied to a method for evaluating and predicting the synergistic effect of bioretention facilities on pollution reduction and carbon reduction in the above embodiments. The system for evaluating and predicting the synergistic effect of bioretention facilities on pollution reduction and carbon reduction includes:

[0088] The data acquisition module is used to collect data on pollutant removal rate, greenhouse gas emissions, and GWP of bioretention facilities with known design parameters and environmental conditions.

[0089] The data processing module is used to preprocess the collected data;

[0090] The model building and application module is used to obtain the pollutant removal rate prediction model and GWP prediction model of bioretention facilities based on robust regression analysis using preprocessed data; input the design parameters and environmental factors of the target bioretention facility into the prediction model to obtain the predicted value of pollutant removal rate and GWP of the target bioretention facility, evaluate its pollution reduction and carbon reduction synergistic effect; and establish a database.

[0091] The key influencing factor identification module is used to determine the positive and negative impacts and their proportions of each influencing factor of the target bioretention facility through standardization and normalization, and to identify the key influencing factors.

[0092] The design parameter and environmental condition optimization selection module is used to select the optimal parameters for the design and construction of the target bioretention facility and its most suitable environmental conditions based on database parameters and key influencing factors, using a random forest algorithm based on the target pollutant removal rate or GWP value.

[0093] The system for evaluating and predicting the synergistic effect of bioretention facilities in reducing pollution and carbon emissions provided in this embodiment of the invention has the same implementation principle and technical effects as the aforementioned method embodiment. For the sake of brevity, any parts not mentioned in this embodiment can be referred to the corresponding content in the aforementioned method embodiment, and will not be repeated here.

[0094] Additionally, refer to Figure 2 As shown, this embodiment of the invention also provides an electronic device, which may include a processor 10, a memory 11, a communication bus 12 and a communication interface 13, and may also include a computer program stored in the memory 11 and run on the processor 10. The processor executes the computer program to implement a method for evaluating and predicting the synergistic effect of bioretention facilities on pollution reduction and carbon reduction in the above method embodiment.

[0095] The processor 10 may, in some embodiments, be composed of integrated circuits, for example, composed of a single packaged integrated circuit, or composed of a plurality of packaged integrated circuits of the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, combinations of various control chips, etc. The processor 10 is the control core of the electronic device, connects various components of the electronic device through various interfaces and lines, and executes programs or modules stored in the memory 11 and calls data stored in the memory 11 to perform various functions and process data of the electronic device.

[0096] The memory 11 may, for example, be an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the above. More specific examples of storage media include a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disc (DVD), a memory stick, a floppy disk, a mechanical encoding device, and any suitable combination of the above.

[0097] Those skilled in the art will appreciate that embodiments of the present application can be provided as methods, systems, electronic devices, or computer program products, etc. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more storage media (including, but not limited to, disk storage, CD-ROMs, optical storage, etc.) having computer usable program code embodied therein.

[0098] It should be noted that the word "comprising" does not exclude the presence of other components or steps than those listed in a claim. The word "a" or "an" preceding the disclosure of a plurality of components does not exclude a plurality of such components. The present application can be implemented by means of hardware comprising several distinct components, and by means of a suitably programmed computer.

[0099] Various embodiments are described in the specification with progressive progression, each embodiment highlighting different aspects from other embodiments, and the same or similar parts between various embodiments can be referred to each other.

[0100] The foregoing description of the disclosed embodiments enables a person skilled in the art to make or use the application. Modifications of these embodiments will occur to persons of skill in the art, and that the appended claims are intended to cover all such modifications that do not depart from the true spirit and scope of the application. Therefore, the application is not limited to the embodiments shown but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for evaluating the synergistic effect of pollution reduction and carbon reduction of a predicted bioretention facility, characterized in that, The method comprises the following steps: S1: collecting data of pollutant removal rate, greenhouse gas emission and GWP of a bioretention facility with known design parameters and environmental conditions; S2: preprocessing the collected data; S3: obtaining a pollutant removal rate prediction model and a GWP prediction model of the bioretention facility based on robust regression analysis method by using the preprocessed data; inputting design parameters and environmental factors of a target bioretention facility into the prediction model to obtain a pollutant removal rate prediction value and a GWP prediction value of the target bioretention facility, evaluate the synergistic effect of pollution reduction and carbon reduction thereof; and establishing a database; In the S1, the design parameters include respectively planting four kinds of plants of canna, vetiver, iris and eight treasure sedum and not planting plants; and the environmental conditions include respectively using sulfamethoxazole, tetracycline and ciprofloxacin three different antibiotics for interference; In the S3, the calculation formula of the robust regression analysis method is: ； wherein is the dependent variable; is the independent variable value; is the regression coefficient for each independent variable, is a constant; and is obtained by the method: ； where is the design matrix ; the transpose of the design matrix ; the inverse of the design matrix ; the resulting matrix is a matrix of rows, where the first row is a constant , and the remaining rows are the regression coefficients for each variable .

2. The method of claim 1, wherein, In the S2, the Huber loss function and t test are used to preprocess the collected data.

3. The method of claim 1, wherein, In the S3, different plant types and added types of antibiotics are taken as independent variables, and the pollutant removal rate and the GWP value are respectively subjected to stable regression, wherein the pollutant removal rate is the COD removal rate, and the following is obtained: The COD removal rate prediction model is: = 75.593 + 0.214 x Canna + 2.201 x Vetiver + 0.302 x Iris + -0.720 x Saxifraga + -4.684 x No plant + 6.796 x Sulfamethoxazole + 7.634 x Tetracycline + 3.942 x Ciprofloxacin; wherein is the predicted value of COD removal; if the plants or antibiotics in the model are included in the bioretention facility, the value of the corresponding plant or antibiotic is recorded as 1, and if not, it is recorded as 0; The GWP prediction model is: = 506.499 + 6.771 x cannas - 0.647 x lavenders - 0.949 x irises + 0.110 x saxifrages + 8.544 x no plants - 136.491 x sulfamethoxazole - 120.319 x tetracycline - 133.533 x ciprofloxacin; wherein is the predicted value of GWP; if the plant or antibiotic in the model is included in the bioretention facility, the value of the corresponding plant or antibiotic is noted as 1, and if not, as 0.

4. The method of claim 1, wherein, The method further comprises: S4: determining the positive and negative influence of each influencing factor of the target bioretention facility and the proportion thereof by standardization and normalization processing, and determining the key influencing factors.

5. The method of claim 4, wherein the method further comprises: The method further comprises: S5: selecting the optimal parameters for designing and constructing the target bioretention facility and the most suitable environmental conditions thereof based on the target pollutant removal rate or GWP value by using the random forest algorithm according to the database parameters and the key influencing factors.

6. A system for assessing the synergistic effect of pollution reduction and carbon sequestration of a predicted bioretention facility, characterized in that, A system for evaluating and predicting the synergistic effect of pollution reduction and carbon reduction of a bioretention facility according to any one of claims 1-5, the system comprising: a data collection module for collecting data of pollutant removal rate, greenhouse gas emission and GWP of a bioretention facility with known design parameters and environmental conditions; a data processing module for preprocessing the collected data; a model establishment and application module for obtaining a pollutant removal rate prediction model and a GWP prediction model of the bioretention facility based on robust regression analysis method by using the preprocessed data; inputting design parameters and environmental factors of a target bioretention facility into the prediction model to obtain a pollutant removal rate prediction value and a GWP prediction value of the target bioretention facility, evaluate the synergistic effect of pollution reduction and carbon reduction thereof; and establishing a database.

7. An electronic device, comprising: A processor and a memory, the memory stores machine executable instructions that can be executed by the processor, and the processor executes the machine executable instructions to implement a method for evaluating and predicting the synergistic effect of pollution reduction and carbon reduction of a bioretention facility according to any one of claims 1-5.

Images